About Limitations at 13:55 , first bullet point, didn't you say that the model predicts an one-hot class per bounding box? doesn't that mean that each grid cell can actually contain up to B classes? thanks for the amazing explanation by the way
Good question...some later versions (YOLOv3 onwards) use binary cross entropy to enable multi-label classification. Not sure why mean squared error was chosen for YOLOv1.
Do I understand correctly that in NOOBJ part ground truth Ci is always zero and in OBJ part ground truth Ci is in [0,1]? th-cam.com/video/svn9-xV7wjk/w-d-xo.htmlsi=pA0UvT1dzNKjNEqv&t=766
This is the best explanation of YOLO I found. Thanks!
Glad you found it helpful!
Most thorough explanation I’ve come across
This is the best explaination I found so far! From india 🇮🇳
This is the best explanation on YOLO! Thank you very much.
This was really clear and precise! thanks :)
Thanks a lot. Really clear one.
very helpful and easy to understand Thanks
so, what yolo does is basically what I have been doing for these captchas for many many years? I love the video
About Limitations at 13:55 , first bullet point, didn't you say that the model predicts an one-hot class per bounding box? doesn't that mean that each grid cell can actually contain up to B classes? thanks for the amazing explanation by the way
Very nicely presented
Cool!!!
4:06 why we take square root of w, h?
The class probability map is only used to do loss calculations?
Thank you so much
Why don't use cross-entropy for the class loss?
Good question...some later versions (YOLOv3 onwards) use binary cross entropy to enable multi-label classification. Not sure why mean squared error was chosen for YOLOv1.
Does this also work for YOLOv8? because YOLOv8 is different from other versions that use free anchor detection. Thank You
On Ground truth slide seem to be a mistake. 8:06 Check x = (16-10)/10 = 0.6 should be and similarly y = (44-4*10)/10 = 0.4
It's a modulus operator
Hi! Your explanation was dope! Mind dropping the source or reference for that model accuracy-speed comparison table?
Appreciate your comment! The full table can be found in the original YOLO paper (arxiv.org/abs/1506.02640).
Do I understand correctly that in NOOBJ part ground truth Ci is always zero and in OBJ part ground truth Ci is in [0,1]? th-cam.com/video/svn9-xV7wjk/w-d-xo.htmlsi=pA0UvT1dzNKjNEqv&t=766
not, I look as much as I want.
That's not "YOLO"
predicted Ci is calculated with IoU if the cell have object, then how to calculate predicted Ci if the cell doesnt have object?
Ortiz Mountains
Simple , clear and excallent ! Thanks for the explanation.
4:10 are u robot?
Click sll the boxes that contains bicyle
Thats how they get training data for there models.